Geometric moment-dependent global sensitivity analysis without simulation data: application to ship hull form optimisation
In this work, we propose and test a method to expedite Global Sensitivity Analysis (GSA) in
the context of shape optimisation of free-form shapes. To leverage the computational burden …
the context of shape optimisation of free-form shapes. To leverage the computational burden …
CarHoods10k: An industry-grade data set for representation learning and design optimization in engineering applications
Large-scale, high-quality data sets are central to the development of advanced machine
learning techniques that increase the effectiveness of existing optimization methods or even …
learning techniques that increase the effectiveness of existing optimization methods or even …
Surrogate modeling of car drag coefficient with depth and normal renderings
B Song, C Yuan, F Permenter… - International …, 2023 - asmedigitalcollection.asme.org
Generative AI models have made significant progress in automating the creation of 3D
shapes, which has the potential to transform car design. In engineering design and …
shapes, which has the potential to transform car design. In engineering design and …
Multitask shape optimization using a 3-d point cloud autoencoder as unified representation
The choice of design representations, as of search operators, is central to the performance
of evolutionary optimization algorithms, in particular, for multitask problems. The multitask …
of evolutionary optimization algorithms, in particular, for multitask problems. The multitask …
Exploiting generative models for performance predictions of 3D car designs
In automotive digital development, engineers utilize multiple virtual prototyping tools to
design and assess the performance of 3D shapes. However, accurate performance …
design and assess the performance of 3D shapes. However, accurate performance …
Feature visualization for 3D point cloud autoencoders
In order to reduce the dimensionality of 3D point cloud representations, autoencoder
architectures generate increasingly abstract, compressed features of the input data …
architectures generate increasingly abstract, compressed features of the input data …
Variational autoencoders for 3D data processing
Variational autoencoders (VAEs) play an important role in high-dimensional data generation
based on their ability to fuse the stochastic data representation with the power of recent …
based on their ability to fuse the stochastic data representation with the power of recent …
Drivaernet: A parametric car dataset for data-driven aerodynamic design and graph-based drag prediction
This study introduces DrivAerNet, a large-scale high-fidelity CFD dataset of 3D industry-
standard car shapes, and RegDGCNN, a dynamic graph convolutional neural network …
standard car shapes, and RegDGCNN, a dynamic graph convolutional neural network …
Quantifying the generative capabilities of variational autoencoders for 3D car point clouds
During each cycle of automotive development, large amounts of geometric data are
generated as results of design studies and simulation tasks. Discovering hidden knowledge …
generated as results of design studies and simulation tasks. Discovering hidden knowledge …
Point2ffd: Learning shape representations of simulation-ready 3d models for engineering design optimization
Methods for learning on 3D point clouds became ubiquitous due to the popularization of 3D
scanning technology and advances of machine learning techniques. Among these methods …
scanning technology and advances of machine learning techniques. Among these methods …